Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    still

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    要求
    -0.07
    89
    -0.06
     快
    -0.06
    神
    -0.06
    .dw
    -0.06
    탈
    -0.06
     стратег
    -0.06
    ِّ
    -0.06
    80
    -0.06
    <Category
    -0.06
    POSITIVE LOGITS
     uprav
    0.07
     kapsam
    0.07
    (prediction
    0.06
    ('--
    0.06
    IBLE
    0.06
     대행
    0.06
     оброб
    0.06
    charAt
    0.06
    iales
    0.06
    _TypeInfo
    0.06
    Act Density 0.033%

    No Known Activations